Multilingual adaptative text simplification
Reading is an essential skill that plays a crucial role in our daily lives. It allows us to access information, gain knowledge, expand our understanding of the world around us, and build the foundation for learning, communication, and personal growth. However, many texts we encounter day after day o...
| Author: | |
|---|---|
| Format: | doctoral thesis |
| Status: | Published version |
| Publication Date: | 2023 |
| Country: | España |
| Institution: | CBUC, CESCA |
| Repository: | TDR. Tesis Doctorales en Red |
| OAI Identifier: | oai:www.tdx.cat:10803/689317 |
| Online Access: | http://hdl.handle.net/10803/689317 |
| Access Level: | Open access |
| Keyword: | Adaptive text simplification Lexical simplification Sentence simplification Complex word identification Controllable lexical and sentence simplification Simplificació adaptativa de text Simplificació lèxica Simplificació de frases Identificació de paraules complexes Simplificació léxica i oracional controlable 62 |
| Summary: | Reading is an essential skill that plays a crucial role in our daily lives. It allows us to access information, gain knowledge, expand our understanding of the world around us, and build the foundation for learning, communication, and personal growth. However, many texts we encounter day after day often contain complex words or syntactic structures that can cause reading difficulties for certain groups of people; this motivates the need for Automatic Text Simplification (ATS). ATS is a Natural Language Processing (NLP) task that aims to reduce the linguistic complexity of a text while preserving its original information and meaning. It involves various operations, such as replacing complex words with simpler synonyms, splitting long sentences into shorter ones, and reorganizing the structure of the text. The goal of ATS is to make texts more accessible and understandable to a broader audience, including non-native speakers, children, and individuals with Dyslexia, Autism, Aphasia, Intellectual Disabilities, and Deaf and Hard of Hearing. In this work, we will discuss our proposed methods for Complex Word Identification (CWI), Lexical Simplification (LS), and Sentence Simplification (SS) in order to help improve reading comprehension. For CWI, we propose several systems based on different machine learning algorithms, such as Convolutional Neural Networks, CatBoost, and XGBoost with word embeddings and feature-engineered for identifying complex words in English, Spanish, German, and French texts. For LS, we propose two systems, monolingual English and multilingual system supporting English, Spanish, and Portuguese. For SS, we propose several systems to simplify English and Spanish texts. In both LS and SS, we explore the use of transfer learning and controllable mechanism, where the transfer learning help create the model that requires less amount of training data, and the controllable mechanism gives us the ability to adjust the outputs based on our preference, especially for different target audiences. |
|---|